Ibm Granite

102 indexed models

102 matching models

ibm-granite/granite-4.1-30b-fp8

azureFoundry/HuggingFace/ibm-granite-granite-4.1-30b-fp8@1

`ibm-granite/granite-4.1-30b-fp8` powered by vLLM - [Original Model Card](https://huggingface.co/ibm-granite/granite-4.1-30b-fp8) - [vLLM Documentation](https://docs.vllm.ai/) ## Chat Completions API ### Send Request You can use cURL or any REST Client to send a request to th

Input modalities
text
Output modalities
text

ibm-granite/granite-4.1-3b-fp8

azureFoundry/HuggingFace/ibm-granite-granite-4.1-3b-fp8@1

`ibm-granite/granite-4.1-3b-fp8` powered by vLLM - [Original Model Card](https://huggingface.co/ibm-granite/granite-4.1-3b-fp8) - [vLLM Documentation](https://docs.vllm.ai/) ## Chat Completions API ### Send Request You can use cURL or any REST Client to send a request to the

Input modalities
text
Output modalities
text

ibm-granite/granite-4.1-3b-GGUF

azureFoundry/HuggingFace/ibm-granite-granite-4.1-3b-gguf@2

`ibm-granite/granite-4.1-3b-GGUF` with Q8_0 quantization, powered by llama.cpp - [Original Model Card](https://huggingface.co/ibm-granite/granite-4.1-3b-GGUF) - [llama.cpp Documentation](https://github.com/ggml-org/llama.cpp) ## GGUF **GGUF** is a binary file format optimized

Input modalities
text
Output modalities
text

ibm-granite/granite-4.1-8b-fp8

azureFoundry/HuggingFace/ibm-granite-granite-4.1-8b-fp8@1

`ibm-granite/granite-4.1-8b-fp8` powered by vLLM - [Original Model Card](https://huggingface.co/ibm-granite/granite-4.1-8b-fp8) - [vLLM Documentation](https://docs.vllm.ai/) ## Chat Completions API ### Send Request You can use cURL or any REST Client to send a request to the

Input modalities
text
Output modalities
text

ibm-granite/granite-4.1-8b-GGUF

azureFoundry/HuggingFace/ibm-granite-granite-4.1-8b-gguf@1

`ibm-granite/granite-4.1-8b-GGUF` with Q8_0 quantization, powered by llama.cpp - [Original Model Card](https://huggingface.co/ibm-granite/granite-4.1-8b-GGUF) - [llama.cpp Documentation](https://github.com/ggml-org/llama.cpp) ## GGUF **GGUF** is a binary file format optimized

Input modalities
text
Output modalities
text

ibm-granite/granite-4.2-30b

azureFoundry/azure-huggingface/ibm-granite--granite-4.2-30b@1

Granite 4.2 30B reasoning model for long-context multilingual chat, coding, and tool use.

Context window
131,072
Input modalities
text
Output modalities
text

ibm-granite/granite-7b-base

azureFoundry/HuggingFace/ibm-granite-granite-7b-base@1

`ibm-granite/granite-7b-base` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/ibm-granite/granite-7b-base) - [Text Generation Inference Documenta

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v2: 7.909%

ibm-granite/granite-docling-258M

vertexAI/publishers/hf-ibm-granite/models/granite-docling-258m@001

Input modalities
image, text
Output modalities
text
Capabilities
multimodal, visionInput

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace